Table 5 Analysis on classifiers of the proposed hybrid + SUCMO model for datasets.

	SVM	ANN	CNN	RF	QNN	GRU-CNN	Hybrid + SUCMO
UNSW-NB15 Dataset
Accuracy	0.881167	0.898583	0.917667	0.891417	0.878889	0.917667	0.933667
Sensitivity	0.998068	0.998068	0.998068	0.834063	0.997187	0.917667	0.93898
Specificity	0.66706	0.716376	0.770411	0.996461	0.662668	0.917667	0.9486
Precision	0.845927	0.865683	0.888417	0.997688	0.843824	0.917667	0.909379
F-measure	0.915721	0.927174	0.940056	0.908568	0.914118	0.917667	0.936891
MCC	0.747756	0.7842	0.824145	0.796554	0.74278	0.835333	0.868224
NPV	0.994722	0.995084	0.995427	0.766286	0.992301	0.917667	0.841257
FPR	0.33294	0.283624	0.229589	0.003539	0.337332	0.082333	0.001912
FNR	0.001932	0.001932	0.001932	0.165937	0.002813	0.082333	0.100819
BoT-IoT Dataset
Accuracy	0.884833	0.893433	0.8352	0.892933	0.906303	0.873133	0.929692
Sensitivity	0.712083	0.733583	0.588	0.732333	0.765758	0.682833	0.920196
Specificity	0.928021	0.933396	0.897	0.933083	0.941439	0.920708	0.929987
Precision	0.712083	0.733583	0.588	0.732333	0.765758	0.682833	0.93009
F-measure	0.712083	0.733583	0.588	0.732333	0.765758	0.682833	0.927879
MCC	0.640104	0.666979	0.485	0.665417	0.707197	0.603542	0.920807
NPV	0.928021	0.933396	0.897	0.933083	0.941439	0.920708	0.929797
FPR	0.071979	0.066604	0.103	0.066917	0.058561	0.079292	0.041385
FNR	0.287917	0.266417	0.412	0.267667	0.234242	0.317167	0.088888

Quick links

Search